"Best Policy Identification in Linear MDPs."

Jérôme Taupin, Yassir Jedra, Alexandre Proutière (2022)

Details and statistics

DOI: 10.48550/ARXIV.2208.05633

access: open

type: Informal or Other Publication

metadata version: 2023-11-28

a service of  Schloss Dagstuhl - Leibniz Center for Informatics